Systems and Methods for Ranking User Capabilities Using Machine Learning Techniques

1. A system, comprising: a memory device; and at least one hardware processor coupled to the memory device, wherein the at least one hardware processor is configured to: receive a plurality of sets of capability data individually describing one of a plurality of users; apply an artificial intelligence model to the plurality of sets of capability data to generate a plurality of sets of vectors individually representing a respective one of the plurality of sets of capability data; generating a plurality of summary vectors individually corresponding to a particular set of the plurality of sets of capability data; receive requirement data associated with a particular asset; generate an asset vector for the particular asset based on the requirement data; determine a plurality of similarity scores individually based on a comparison of a corresponding summary vector of the plurality of summary vectors to the asset vector; and generate a ranking of the plurality of users for the particular asset based on the plurality of similarity scores.

2. The system of claim 1, wherein the plurality of similarity scores comprise a plurality of cosine similarity scores.

3. The system of claim 1, wherein the at least one hardware processor is further configured to apply the artificial intelligence model by: generating a plurality of sets of tokenized capability data by applying a tokenizer algorithm to the plurality of sets of capability data; and generating a respective plurality of token vectors for each set of the plurality of sets of tokenized capability data.

4. The system of claim 3, wherein each summary vector of the plurality of summary vectors correspond to an average of the plurality of token vectors for a respective set of the plurality of sets of tokenized capability data.

5. The system of claim 1, wherein the at least one hardware processor is further configured to: generate a plurality of entity matching scores individually corresponding to the plurality of users; and generate a plurality of overall scores for each of the plurality of users based on the plurality of entity matching scores and the plurality of the plurality of similarity scores.

6. The system of claim 5, wherein the at least one hardware processor is further configured to generate the ranking of the plurality of users for the particular asset according to the plurality of overall scores.

7. The system of claim 1, wherein the at least one hardware processor is further configured to generate an asset vector for the particular asset based on the requirement data by applying the artificial intelligence model to the requirement data.

8. The system of claim 1, wherein the at least one hardware processor is further configured to generate a ranking of the plurality of users for the particular asset based on the plurality of similarity scores by generating a compatibility ranking using a large language model.

9. The system of claim 8, wherein the compatibility ranking further comprises a ranking of the plurality of users and a generated description for each of the plurality of sets of capability data.

10. The system of claim 8, wherein the artificial intelligence model further comprises a Longformer model.

11. A method, comprising: receiving, via one of one or more computing devices, a plurality of sets of capability data individually describing one of a plurality of users; applying, via one of the one or more computing devices, an artificial intelligence model to the plurality of sets of capability data to generate a plurality of sets of vectors individually representing a respective one of the plurality of sets of capability data; generating, via one of the one or more computing devices, a plurality of summary vectors individually corresponding to a particular set of the plurality of sets of capability data; receiving, via one of the one or more computing devices, requirement data associated with a particular asset; generating, via one of the one or more computing devices, an asset vector for the particular asset based on the requirement data; determining, via one of the one or more computing devices, a plurality of similarity scores individually based on a comparison of a corresponding summary vector of the plurality of summary vectors to the asset vector; and generating, via one of the one or more computing devices, a ranking of the plurality of users for the particular asset based on the plurality of similarity scores.

12. The method of claim 11, further comprising generating the ranking by generating a compatibility ranking using a large language model comprising a ranking of the plurality of users and a generated description for each of the plurality of sets of capability data.

13. The method of claim 12, wherein the artificial intelligence model further comprises a Longformer model.

14. The method of claim 11, further comprising generating at least one contextual embedding from a particular capability data of the plurality of sets of capability data.

15. The method of claim 11, further comprising: generating, via one of the one or more computing devices, a plurality of entity matching scores individually corresponding to the plurality of users; generating, via one of the one or more computing devices, a plurality of overall scores for each of the plurality of users based on the plurality of entity matching scores and the plurality of the plurality of similarity scores; and generating, via one of the one or more computing devices, the ranking of the plurality of users for the particular asset according to the plurality of overall scores.

16. The method of claim 11, further comprising generating, via one of the one or more computing devices, an asset vector for the particular asset based on the requirement data by applying the artificial intelligence model to the requirement data.

17. A non-transitory computer-readable medium embodying a program that, when executed by at least one computing device, causes the at least one computing device to: receive a plurality of sets of capability data individually describing one of a plurality of users; apply an artificial intelligence model to the plurality of sets of capability data to generate a plurality of sets of vectors individually representing a respective one of the plurality of sets of capability data; generate a plurality of summary vectors individually corresponding to a particular set of the plurality of sets of capability data; receive requirement data associated with a particular asset; generate an asset vector for the particular asset based on the requirement data; determine a plurality of similarity scores individually based on a comparison of a corresponding summary vector of the plurality of summary vectors to the asset vector; and generate a ranking of the plurality of users for the particular asset based on the plurality of similarity scores.

18. The non-transitory computer-readable medium of claim 17, wherein program further causes the at least one computing device to modify a particular set of the plurality of sets of vectors based on context of at least one surrounding tokens.

19. The non-transitory computer-readable medium of claim 17, wherein program further causes the at least one computing device to: generate a plurality of sets of tokenized capability data by applying a tokenizer algorithm to the plurality of sets of capability data; and generate a respective plurality of token vectors for each set of the plurality of sets of tokenized capability data, wherein each summary vector of the plurality of summary vectors correspond to an average of the plurality of token vectors for a respective set of the plurality of sets of tokenized capability data.

20. The non-transitory computer-readable medium of claim 17, wherein program further causes the at least one computing device to: generate a plurality of entity matching scores individually corresponding to the plurality of users; and generate a plurality of overall scores for each of the plurality of users based on the plurality of entity matching scores and the plurality of the plurality of similarity scores.